Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

Abstract

In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization approach, called cross pseudo supervision (CPS). Our approach imposes the consistency on two segmentation networks perturbed with different initialization for the same input image. The pseudo one-hot label map, output from one perturbed segmentation network, is used to supervise the other segmentation network with the standard cross-entropy loss, and vice versa. The CPS consistency has two roles: encourage high similarity between the predictions of two perturbed networks for the same input image, and expand training data by using the unlabeled data with pseudo labels. Experiment results show that our approach achieves the state-of-the-art semi-supervised segmentation performance on Cityscapes and PASCAL VOC 2012. Code is available at https://git.io/CPS.

arXiv commentAccepted by CVPR 2021

References in corpus (8)

• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• OCNet: Object Context Network for Scene Parsing
• Rethinking Pre-training and Self-training
• Adversarial Learning for Semi-Supervised Semantic Segmentation
• Deep High-Resolution Representation Learning for Visual Recognition
• Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
• Structured Consistency Loss for semi-supervised semantic segmentation
• Improving Semantic Segmentation via Self-Training

Cited by in corpus (4)

• Self-Training: A Survey
• Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation
• Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
• Quantifying Topology In Pancreatic Tubular Networks From Live Imaging 3D Microscopy